INDEX

Explanations

numerical values or identifiers in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ongo

-0.19

xo

-0.15

apiro

-0.15

ing

-0.14

ampo

-0.14

ureau

-0.14

xis

-0.14

.yahoo

-0.14

ocop

-0.14

à¸ĩà¸²à¸Ļ

-0.14

POSITIVE LOGITS

TOD

0.17

 airl

0.15

¿ł

0.14

-sama

0.14

Ñİ

0.14

ovah

0.13

urs

0.13

nbsp

0.13

 Spare

0.13

 Venez

0.13

Activations Density 0.043%

numerical values or identifiers in various contexts

No Comments

No Known Activations